guancongluo/semantic-histogram-based-global-localization

Semantic graph based global localization for multi-robot map fusion.

Semantic Histogram Based Graph Matching for Real-Time Multi-Robot Global Localization in Large Scale Environment

Related Publications:

Xiyue Guo, Junjie Hu, Junfeng Chen, Fuqin Deng, Tin Lun Lam, Semantic Histogram Based Graph Matching for Real-Time Multi-Robot Global Localization in Large Scale Environment, IEEE Robotics and Automation Letters, 2021. PDF.

Results

1. Prerequisites

• Ubuntu = 20.04
• CMake = 3.16.3
• Eigen = 3.3.7
• Pangolin - master
• OpenCV = 4.5.4
• PCL = 1.10

2. Running

Clone the repository and catkin_make:

    git clone https://https://github.com/gxytcrc/Semantic-Graph-based--global-Localization.git
    mkdir build
    cd build
    cmake ..
    make -j4

Download the dataset that is created from Airsim, and save them into the Datset . Download link: https://drive.google.com/file/d/106sPA48vFThLK0RB4WBcj-i8FZPQPmcV/view?usp=sharing.

Launch it as follows:

./mapAlignment robot1-foldername startFrameNumber endFrameNumber robot2-foldername startFrameNumber endFrameNumber

eg:

 ./mapAlignment forwardCar 0 343 backwardCar 0 300

可视化： 前提 sudo apt install pcl-tools 同时显示两个点云： pcl_viewer cloud1.pcd cloud2pcd 修改点云颜色显示： pcl_viewer -fc 0,255,0 cloud1.pcd -fc 0,0,255 cloud2pcd

Citation

@inproceedings{XiyueGuo2021,
title={Semantic Histogram Based Graph Matching for Real-Time Multi-Robot Global Localization in Large Scale Environment},
author={Xiyue Guo, Junjie Hu, Junfeng Chen, Fuqin Deng, Tin Lun Lam},
booktitle=IEEE Robotics and Automation Letters (RA-L)},
year={2021}
}